Embedding & reranker services
11 systems in the embedding & reranker services category of the AI Agent Infrastructure Landscape, grouped by maturity tier.
Tier 1 — battle-tested (6)
- Cohere Embed Hosted embeddings API
Cohere's hosted embedding models, now Embed 5 (2026-09-30; Pro and Fast tiers): text, image and fused text-plus-image inputs, 100+ languages, 128K-token context, Matryoshka output dimensions from 256 to 2048 with float, int8 and binary f…
- Hugging Face Inference API (Embeddings) HF hosted embeddings
HF's hosted Inference API and Inference Endpoints — serve any model from the Hub including the BGE/GTE/E5 embedding families.
- Jina AI Embeddings Open embedding models + API
Jina AI's embedding family — jina-embeddings-v3 (multilingual), jina-clip-v2 (text+image), jina-colbert-v2. Open-weights + hosted API + ColBERT-style.
- OpenAI Embeddings OpenAI embedding API
OpenAI's hosted embedding API — text-embedding-3-small, text-embedding-3-large. Most widely used commercial embedding API in OSS RAG/memory stacks.
- Sentence Transformers Open embedding training framework
Reimers & Gurevych's library for training sentence embeddings — substrate under most open-weight embedding models. Now under Hugging Face.
- Voyage AI (MongoDB) Premium embedding + reranker API
Specialised embedding and reranker provider — voyage-3, voyage-multilingual, voyage-finance, voyage-law, voyage-code. Acquired by MongoDB Feb 2025 for $220M.
Tier 2 — production-ready (4)
- BGE (BAAI) BAAI open embedding family
BAAI (Beijing Academy of AI) BGE family — bge-large/base/small + bge-m3 multilingual + bge-reranker. One of the most widely-used open embedding families.
- Mistral Embed Mistral embedding API
Mistral AI's hosted embedding API — mistral-embed; available via Mistral La Plateforme and Azure AI.
- Mixedbread AI Embedding + reranker API
Agentic search platform that ingests PDFs, decks, video, code, Slack and Drive and returns evidence to agents. Built on its own models and database: Wholembed V3 (late-interaction, omnimodal) embeddings, mxbai-rerank listwise reranker, a…
- Nomic Embed Open embedding + atlas
Nomic's open-weight embedding models (nomic-embed-text-v1.5, nomic-embed-vision), distributed on Hugging Face. Nomic itself has pivoted to domain-specific agents for architecture, engineering and construction firms (Nomic Platform, Agent…
Tier 3 — emerging (1)
- GTE (Alibaba-NLP) Alibaba general text embeddings
Alibaba DAMO Academy's GTE family — open-weight multilingual embedding models; gte-large/base/small + Qwen-based gte-Qwen2.